cmenet: a new method for bi-level variable selection of conditional main effects. This paper presents a novel method for selecting main effects and a set of reparametrized predictors called conditional main effects (CMEs), which capture the conditional effect of a factor at a fixed level of another factor. CMEs represent highly interpretable phenomena for a wide range of applications in engineering, social sciences and genomics. The challenge in model selection lies in the grouped collinearity structure of CMEs, which can cause poor selection and prediction performance for existing methods. We propose a new method called cmenet, which employs coordinate descent and two principles called CME coupling and reduction to efficiently perform model selection. Simulation studies demonstrate the improved performance of cmenet over existing selection methods, such as the LASSO and SparseNet. Applied to a gene association study on fly wing shape, cmenet not only provides improved predictive performance over existing techniques, but also reveals important insight on gene activation behavior. Efficient implementations of our algorithms are available in the R package cmenet in CRAN.
Keywords for this software
References in zbMATH (referenced in 8 articles )
Showing results 1 to 8 of 8.
- Xie, Weijun; Deng, Xinwei: Scalable algorithms for the sparse ridge regression (2020)
- Chang, Ming-Chung: De-aliasing in two-level factorial designs: a Bayesian approach (2019)
- Mak, Simon; Wu, C. F. Jeff: \textsfcmenet: A new method for bi-level variable selection of conditional main effects (2019)
- Sabbaghi, Arman: An evaluation of estimation capacity under the conditional main effect parameterization (2019)
- Wu, C. F. Jeff: A fresh look at effect aliasing and interactions: some new wine in old bottles (2018)
- Wu, C. F. Jeff: Rejoinder (2018)
- Yoshida, Ryo: Discussion on the paper by Professor Wu (2018)
- Simon Mak, C. F. Jeff Wu: cmenet: a new method for bi-level variable selection of conditional main effects (2017) arXiv